Tabbit
ResourcesBlogModels
Tabbit LogoTabbit

Tabbit — The AI Browser that Works for You

Topics

  • AI Browser Resources
  • Agentic Browser Resources
  • Browser Downloads and Install Guides
  • Browser Comparisons
  • AI Browser Alternatives
  • Browser Productivity Resources

Popular Guides

  • AI Browser
  • Agentic Browser Download
  • Best AI Browser 2026: Top 9 Tested & Ranked
  • AI Browser Download
  • Free AI Browser
  • Best AI Browser 2026
  • AI Browser Comparison 2026
  • AI Browser for Windows
  • AI Browser for Mac
  • Chrome Alternative 2026

Events

  • Tabbit Skill Competition
  • KPOP SBTI Fandom Personality Test
  • Tabbit Campus Creator Program
  • fifi's Picks: AI Skills for Research Papers
  • User Survey

About

  • Tabbit Blog
  • Press & Media
Prompt guide
CommunityGPT-5.6 Terra

GPT-5.6 Multi-Agent Routing Rules for Codex Agent.md

Original source

X

Author苏打白.Dev (@sodawhitedev)

Source date2026-08-16

Tabbit curation2026-08-20

Read original

One-sentence takeaway

Adding task-complexity-to-model routing rules to Agent.md enables the primary Codex agent to dynamically assign sub-tasks to Sol, Terra, or Luna based on complexity when tasks are decomposable, while avoiding unnecessary sub-agent invocation for simple tasks.

Suitable use cases

  • Suitable tasks: Codex Multi-Agent V2, decomposable coding or analytical tasks, and agent orchestration requiring quota/token usage control.

  • Unsuitable tasks: Non-decomposable sequential tasks, tasks where all steps must share real-time context, and high-risk write operations lacking automated or human verification.

  • Applicable model versions: GPT-5.6 Sol, GPT-5.6 Terra, and GPT-5.6 Luna; no specific snapshot was specified in the original post.

  • Applicable clients, agents, or APIs: Codex's Agent.md or root prompt; not intended as a general API system prompt.

  • Recommended reasoning effort and parameters: Determined dynamically by the primary agent based on sub-task complexity; the original post specifies no explicit effort parameters.

Copy-ready content

Add the following content to your project's Agent.md (verify the filename and supported model IDs according to your Codex version):

Sub-agents may be used when a task can be decomposed into two or more independent workflows.
The primary agent selects the model based on sub-task complexity:
- Complex planning, architecture, and critical decision-making: gpt-5.6-sol
- Routine analysis, coding, and execution: gpt-5.6-terra
- Well-defined, repetitive, search, scanning, and cleanup tasks: gpt-5.6-luna
Do not spawn sub-agents for simple tasks. Unless explicitly specified otherwise, the primary agent determines the sub-agent's model and reasoning effort.

How to use

  1. Place these rules in the project-level Agent.md or the corresponding root prompt that Codex reads.

  2. Only allow delegation when two or more mutually independent workflows exist.

  3. Have the primary agent evaluate task complexity before selecting the sub-agent model and reasoning effort.

  4. Route complex planning and architecture to Sol, routine analysis and coding to Terra, and repetitive search or scanning to Luna.

  5. Keep simple tasks on a single agent; ensure tests, code reviews, or manual confirmation remain in place for critical writes.

Boundaries

  • This is a community-shared routing rule rather than an official OpenAI default system prompt, and no public benchmark experiments on success rates or token quota efficiency were provided.

  • Model routing alone does not resolve permissions, sandboxing, concurrency, or output verification; these remain the responsibility of Codex configuration and project workflows.

  • Model IDs like gpt-5.6-*, Agent.md loading behavior, and multi-agent capabilities may change across Codex versions; verify against current client documentation before use.

Curated by Tabbit

Prompt material is summarized from public sources and Tabbit editorial notes. Check the original licensing and intended use before copying it.

GPT-5.6 Terra

Use in Tabbit

GPT-5.6 Terra

Related prompts

OfficialOpenAI Developers

GPT-5.6 Terra API Model Parameters and Tool Configuration

OfficialOfficial OpenAI release2026-07-09

GPT-5.6 Terra Frontend Interaction Prototype Prompts and Validation Workflow

MediaDataCamp2026-08-04

GPT-5.6 Terra Long-Context Cost Thresholds and Routing Workflow

CommunityX2026-08-01

Generating Entrance Animations and Layout Variations in Framer Agent with GPT-5.6 Terra

GPT-5.6 Terra

Related reviews

OfficialOpenAI Deployment Safety Hub2026-07-09

GPT-5.6 Terra System Card: Safety Guardrails and Agent Boundaries

OfficialSonarSource2026-08-06

GPT-5.6 Terra: SonarSource's Retest of Code Quality and Security on 4,444 Java Tasks

OfficialOpenAI official launch page2026-07-10

Official OpenAI GPT-5.6 Terra Benchmarks, Pricing, and Task Boundaries

MediaArtificial Analysis2026-07-09

GPT-5.6 Terra: Artificial Analysis Intelligence, Cost, and Coding Agent Indices